Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setup
    -0.07
    _inv
    -0.07
     растение
    -0.06
    Finding
    -0.06
    ализа
    -0.06
     stick
    -0.06
    “,
    -0.06
     formats
    -0.06
     waar
    -0.06
     dancing
    -0.06
    POSITIVE LOGITS
     GLES
    0.07
    668
    0.06
    alesce
    0.06
     Notices
    0.06
     leaked
    0.06
     ">↵
    0.06
    *****↵↵
    0.06
    Detail
    0.06
     Candle
    0.06
    _LANGUAGE
    0.06
    Act Density 0.004%

    No Known Activations